一种基于小波包分析和神经网络的笔迹鉴别方法
|
摘要
基于笔迹的计算机身份鉴别是目前活跃于模式识别和图像处理领域的研究热点之一。小波分析具有出色的时间—频率域多分辨特性，十多年米在信息处理领域得到了迅速的发展。将小波分析引入到计算机笔迹鉴别中，探寻一些分布于不同频率域中的笔迹特征成为了计算机笔迹鉴别研究的一条新思路。
笔者将笔迹的书写过程理解为笔迹能量的空间分布过程。基于这一观点，笔者提出了一整套计算机笔迹纹理特征分析方法。首先，笔者提出了一种与传统方法截然不同的笔迹归一化办法，它即能够充分保留笔迹样本的空间分布信息，又可以有效的简化笔迹的预处理过程。接着，本文论述了一种与较常出现的小波基匹配降维方法有着本质区别的二维小波包最好基特征提取方法。该方法直接在二维空间上由db6小波包基对笔迹纹理实施3尺度小波包分解，再在由以香农熵为代价函数提取得到的15个小波包最好基处对分解系数实行重构。为了更好的描述这15个子纹理图像所包含的能量特征，本文提出了一种被称为非线性能量测度的子纹理图像能量特征值实现方法，实验证明这种办法具有纹理自适应匹配的能力。经过上述一系列处理后，一个汉字笔迹图像可以被压缩为一个含有15个元素的能量测度矩阵。将分解得到的各能量测度矩阵的组合经规范化后由BP神经网络进行学习和分类，实践证明此笔迹鉴别系统对实验中提取的有限样本的鉴别正确率可达95％以上。
本系统已由C++和Matlab混合编程实现。
The computer writer identification based on handwriting is one of the research focuses in the field of Pattern Recognition and Image Processing. Because wavelet analysis has excellent characteristic in Timefrequency Multiresolution, it has been rapidly developed in the field of Information Processing in recent ten years. Applying wavelet analysis to computer handwriting identification and exploring some handwriting characteristic distributed in different frequency domains have become a new research idea of computer handwriting identification.
The writing process is regarded as the distributing process of handwriting energy by author. According to this point of view, a set of characteristic analysis methods for computer handwriting texture are presented. Firstly, author presents a normalization method which is entirely different to tradititnal methods. The method can not only retain the spatial information of handwriting samples, but also efficiently simplify the preprocessing of them. Secondly, a 2-D Wavelet Packet best basis characteristic extraction method which is essentially different to the familiar basis matching method is described. The method directly executes wavelet packet decomposition of handwriting texture using wavelet packet basis db6 at scaling 3 in 2D space, then reconstructs the decomposition coefficient of 15 wavelet packet best basis which are took by Shannon Entropy Cost Function. In order to obtain the energy characteristic of texture sub-image, a nonlinear handwriting energy measure method is presented in this pape
r. It has been proved that the method has the adaptive capability to match the texture. After a series of above-mentioned processing, a Chinese character image can be compressed into an energy measure matrix which includes 15 elements. A BP Neural Networks is designed to learn and classify the result coming fom the combination and standardization of every energy measure matrix.The experiment proves that the recognition rate of the system can reach to 95% or more when the number of the experimental sample is limited.
This system is implemented by mixed programing based on C++ and Matlab.
笔者将笔迹的书写过程理解为笔迹能量的空间分布过程。基于这一观点，笔者提出了一整套计算机笔迹纹理特征分析方法。首先，笔者提出了一种与传统方法截然不同的笔迹归一化办法，它即能够充分保留笔迹样本的空间分布信息，又可以有效的简化笔迹的预处理过程。接着，本文论述了一种与较常出现的小波基匹配降维方法有着本质区别的二维小波包最好基特征提取方法。该方法直接在二维空间上由db6小波包基对笔迹纹理实施3尺度小波包分解，再在由以香农熵为代价函数提取得到的15个小波包最好基处对分解系数实行重构。为了更好的描述这15个子纹理图像所包含的能量特征，本文提出了一种被称为非线性能量测度的子纹理图像能量特征值实现方法，实验证明这种办法具有纹理自适应匹配的能力。经过上述一系列处理后，一个汉字笔迹图像可以被压缩为一个含有15个元素的能量测度矩阵。将分解得到的各能量测度矩阵的组合经规范化后由BP神经网络进行学习和分类，实践证明此笔迹鉴别系统对实验中提取的有限样本的鉴别正确率可达95％以上。
本系统已由C++和Matlab混合编程实现。
The computer writer identification based on handwriting is one of the research focuses in the field of Pattern Recognition and Image Processing. Because wavelet analysis has excellent characteristic in Timefrequency Multiresolution, it has been rapidly developed in the field of Information Processing in recent ten years. Applying wavelet analysis to computer handwriting identification and exploring some handwriting characteristic distributed in different frequency domains have become a new research idea of computer handwriting identification.
The writing process is regarded as the distributing process of handwriting energy by author. According to this point of view, a set of characteristic analysis methods for computer handwriting texture are presented. Firstly, author presents a normalization method which is entirely different to tradititnal methods. The method can not only retain the spatial information of handwriting samples, but also efficiently simplify the preprocessing of them. Secondly, a 2-D Wavelet Packet best basis characteristic extraction method which is essentially different to the familiar basis matching method is described. The method directly executes wavelet packet decomposition of handwriting texture using wavelet packet basis db6 at scaling 3 in 2D space, then reconstructs the decomposition coefficient of 15 wavelet packet best basis which are took by Shannon Entropy Cost Function. In order to obtain the energy characteristic of texture sub-image, a nonlinear handwriting energy measure method is presented in this pape
r. It has been proved that the method has the adaptive capability to match the texture. After a series of above-mentioned processing, a Chinese character image can be compressed into an energy measure matrix which includes 15 elements. A BP Neural Networks is designed to learn and classify the result coming fom the combination and standardization of every energy measure matrix.The experiment proves that the recognition rate of the system can reach to 95% or more when the number of the experimental sample is limited.
This system is implemented by mixed programing based on C++ and Matlab.
引文
[1]戴汝为，郝红卫，肖旭红．智能自动化丛书—汉字识别的系统与集成．浙江科学技术出版社，1998年12月．
[2]朱勇，谭铁牛等．基于笔迹的身份鉴别．自动化学报．第27卷，第二期，2001年3月．
[3]Kenneth R. Castleman著，朱志刚等译．数字图象处理．电子工业出版社，2001年3月．
[4]边肇祺，张学工著．模式识别．清华大学出版社，2000年3月．
[5]陈武凡主编．小波分析及其在图象处理中的应用．科学出版社，2002年4月．
[6]C. K. Chui. An introduction to wavelet New York, Academic Press 1992.
[7]胡昌华．基于MATLAB的系统分析与设计—小波分析．西安电子科技大学出版社，1999年12月．
[8]郑治真，沈萍等．小波变换及其Matlab工具的应用．地震出版社，2001年10月．
[9]李建平主编．小波分析与信号处理—理论、应用及软件实现．重庆出版社，1997年2月．
[10]马兴义，杨立群等．Matlab 6应用开发指南．机械工业出版社，2002年1月．
[11]张德干．小波变换在数字图象处理中的应用研究．硕士学位论文，东北大学．2000年．
[12]陈自利．基于小波与神经网络的文字识别系统研究．博士学位论文，重庆大学．1999年．
[13]江亚东．KDD系统中基于小波神经网络的混沌模式提取与混沌时间序列预测的研究．博士学位论文，北京科技大学．2002年．
[14]钱峻．小波神经网络建摸研究与现场总线控制系统的集成．博士学位论文，上海交通大学．2000年．
[15]孟波．基于小波分析的数据挖掘方法研究．博士学位论文，南京大学．1994年．
[16]黄源．基于神经网络的数据挖掘技术研究研究．博士学位论文，南京大学．1994年．
[17]钱能主编．C++程序设计教程．清华大学出版社，1999年4月．
[18]Jon Bates，Tim Tompkins著，何健辉等译实用Visual C++6.0教程．清华大学出版社，2000年8月．
[19]向世明．Visual C++数字图象与图形处理．电子工业出版社，2002年3月．
[20]北京博彦科技发展有限公司．Visual C++编程高手．北京大学出版社，2000年11月．
[21]张青，尹俊勋．小波变换在手写体汉字识别中的应用．电路与系统学报，1996，(3)，63-67．
[22]张德于，郝先臣等．基于小波理论的数据挖掘方法研究．小型微型计算机系统，2001，22(8)，946-949．
[23]陈哲，冯天谨．小波分析与神经网络结合的研究进展．电子科学学刊，2000，22(3)，496-504．
[24]冯兵等．HMM方法识别脱机手写体汉字．模式识别与人工智能，2002，15(1)，84-88．
[25]金连文，黄建成等．变形变换及其在手写体汉字整形中的应用．中国图象图形学报，2002，7(2)，170-175．
[26]付新文，张妙兰等．基于小波生成特征符号随机场的纹理匹配与分类．中国图象图形学报，1999，4(3)，243-246．
[27]张睿，丁晓青等．脱机手写汉字识别的最优采样特征新方法．中国图象图形学报，2002，7(2)，176-180．
[28]文颖，龚裕等．基于基本笔画运笔特征的汉字笔迹鉴定的研究．上海交通大学学报(自然科学版)，2002，8(1)，39-43．
[29]杨懂峰等．计算机自动笔迹鉴定关键技术研究．计算机技术与自动化，2002，21(2)，27-34．
[30]刘成林等．基于多通道分解与匹配的笔迹鉴别研究．自动化学报，1997，23(1)，56-63．
[31]刘成林，戴汝为等．笔迹鉴别的字符预处理与匹配．中文信息学报，1996，10(3)．
[32]刘成林等．简化的Wigner分布及其在笔迹鉴别中的应用．计算机学报，1997，20(11)．
[33]林湘宁，刘沛等．小波分析基础理论及其在电力系统中的应用．电力系统自动化，1997，21(10)．
[34]许东，吴铮．基于MATLAB 6.x的系统分析与设计—神经网络．西安电子科技大学出版社，2002年5月．
[35]R. Plamondon and G. Lorret. Automation Signature Verification and Writer Identification-the State of Art. Pattern Recognition. 1989,22(2), 107-131.
[36]P. S. Deng, H. M. Liao, C. W. Ho and H. R. Tyan. Wavelet-based Off-line Signature Verification. http: //www.iis.sinica.edu.tw/LIB/threebone9717.html.
[37]Y. Y. Tang, F. Yang and J. Liu. Basic Processes of Chinese Character Based on Cubic BSpline Wavelet Transform. IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 23, no. 12, pp. 1443-1448, 2001.
[38]S. Sasi, L. Schwiebert and J. S. Bedi. Wavelet Packet Transform and Neuro Fuzzy Approach to Handwritten Character Recognition Signal and Image Proc. Conf.. 1997,12, pp. 129-133.
[39]R. S. R. Kunte, and R. D. S. Samuel. On-line Character Recognition for Handwritten Kannada Characters Using Wavelet Feature and Neural Classifier IETE Joural of Research. Vol. 46, no. 5, pp. 387-392, 2000.
[40]C. Barrire and R. Plamondon. Human Identification of Letter in MixedScript Handwriting: an Upper Bound on Recognition Rates IEEE Trans. On System, Man, and Cyber.-part B: Cyber. Vol. 28, no. 1, pp. 78-81, 1998.
[41]I. P. Morns and S. S. Dlay. Analog Design of a New Neural Network for Optical Charater Recognition. IEEE Trans. On Neural Networks. Vol. 10, no. 4, pp. 951-953, 1999.
[42]I. P. Morns and S. S. Dlay. The DSFPN, a New Neural Network for Optical Charater
Recongnition IEEE Trans. On Neural Networks. Vol. 10, no. 6, pp. 1465-1473, 1999.
[43]C. K. Tan, Y. L. Soh and C. Y. Woo. A Novel Method of Online Handwritten Chinese Word Verification. http://www. wbmt. tudelft.nl/pto/research/conferences/Proceedings/icsc/pdf.
[44]U. Bhattacharya, T. K. Das and B. B. Chaudhuri. A Cascaded Scheme for Recognition of Handprinted Numbers The 3rd Indian Conf. on Computer Vision, Graph. and Image Proc., Oral Session2: OCR. 2002.
[45]D. Shi, S. R. Gunn and R. I. Damper. A Radical Approach to Handwritten Chinese Character Recognition Using Active Handwriting Models Proc. IEEE Conf. On Computer Vision and Pattern Recognition. pp. 670-675, 2001.
[46]M. Morita, R. Sabourin et al. Segmentation and Recognition of Handwritten Dates The 8th Inter. Workshop on Frontiers in Handwriting Recognition. 8, 1999.
[47]R. Plamondon and N. Srihari. On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 22, no. 1, pp. 63-84, 2000.
[48]S. E. N. Correia et al. On the Performance of Wavelets for Handwritten Numerals Recognition The 16th Inter. Conf. on Pattern Recognition. Vol. Ⅲ, pp. 127-130, 2002.
[49]A. Mojsilovic, M. Popovic and J. Marinkovic. Texture Analysis and Classification with the Nonseparable Wavelet Transform. Circulation, 8, 1998.
[50]T. D. But and G. Chen. Invariant FourieWavelet Descriptor for Pattern Recognition Pattern Recognition. Vol. 32, no. 7, pp.1083-1088, 1999.
[51]G. Y. Chen. Application of Wavelet Transforms in Pattern Recogniion andDe-noise. MCS Thesis. Concordia University, Canada 1999,1.
[52]A. Vinviarelli. A Survey on Off-Line Cursive Script Recognition IDIAP-RR 00-43. 2000.
[53]S. E. U. Correia el al. Human-Perception Handwritten Character Recognition using Wavelets http://www.livia.etsmtl.ca/common/pub_2OO2.html.
[54]X. Gao, L. W. Jin, J. X. Yin and J. C.Huang. SVM-based Handwritten Chinese Character Recognition http://www.cse.cuhk.edu.hk/～apnna/proceedings/iconip2OO1/author/g.htm.
[55]S. Omachi, F. Sun and H. Aso. Precise Recognition of Blurred Chinese Characters by Considering Change in Distribution Proc. Of the 10th Scandinavian Conf. on Image Analysis. pp. 501-506, 1997.
[56]N. Rajpoot. Texture Classification Using Discriminant Wavelet Packet Subbands Proc. Of the 10th IEEE Midwest Symp. on Circuits and Systems, 2002.
[57]A. K. Pujari el al. An Adaption Character Recognition for Telugu Scripts using Multiresolution Analysis aud Associative Memory The 3rd Indian Conf. on Computer Vision, Graph. and
Image Proc., Oral Session2: OCR. 2002.
[58]P. J. Burr and E. H. Adelson. The Laplacian Pyamid as a Compact Image CodelEEE Trans, C-31. pp. 532-540, 1983.
[59]E. A. Fadhel and P. Bhattacharyya. Application of a Steerable WaveletTransform using Neural Network for Signature Verification Pattern Analysis and Applications. Vol. 2, Issue 2, pp. 184-195, 1999.
[60]C. C. Tappert et al. The State of the Art in On-line Handwriting Recognition IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 12, no. 8, pp. 787-805, 1990.
[61]E. Mandler, R. Oed. and W. Doster. Experiments in on-line script recognition, in Proc. 4th Scan-dinavian Conf. Image Anal. June, pp. 75-86, 1985.
[62]K. Huang and H. Yan. Off-line Signature Verification Based on Geometric Feature Extraction and Neural Network Classification Pattern Recognition. Vol. 30, no. 1, pp. 9-17, 1997.
[63]G. Y. Chen, T. D. Bui and A. Krzyzak Contour-Based Handwritten Recognition using Multiwavelet and Neural Networks Pattern Recognition. Vol. 36, no. 7, pp. 1597-1604, 2003.
[64]T. R. Reed and H. Wechsler. Segmentation of Tectured images and Gestart Organization using Spatial/Spatial-Frequency Representation IEEE Trans on PAMI. Vol. 12, no. 1, pp. 1-12, 1990.
[65]Y. Itoh et al. A Study on Estimation of High Resolution Component for Image Enhancement using Wavelet. Proc. Of the 7th ACM Inter. Conf. on Multimedia. Part: 2, 1999.
[66]S. Mallat and S. F. Zhong Characterization of Signals from Multiscale Edges IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 14, no. 7, pp. 710-732, 1992.
[67]S. Mallat. A Theory for Multiresolulion Signal Decomposition The Wavelet Representation IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 11, no. 7, pp. 674-693, 1989.
[68]M. Feil and A. Uhl. 2-D Wavelet Packet Decomposition on Multicomputers. Proc, of the 8th Euromicro Workshop on Parallel and Distributed Proc, IEEE Computer Society. pp.351-356. 2000.
[2]朱勇，谭铁牛等．基于笔迹的身份鉴别．自动化学报．第27卷，第二期，2001年3月．
[3]Kenneth R. Castleman著，朱志刚等译．数字图象处理．电子工业出版社，2001年3月．
[4]边肇祺，张学工著．模式识别．清华大学出版社，2000年3月．
[5]陈武凡主编．小波分析及其在图象处理中的应用．科学出版社，2002年4月．
[6]C. K. Chui. An introduction to wavelet New York, Academic Press 1992.
[7]胡昌华．基于MATLAB的系统分析与设计—小波分析．西安电子科技大学出版社，1999年12月．
[8]郑治真，沈萍等．小波变换及其Matlab工具的应用．地震出版社，2001年10月．
[9]李建平主编．小波分析与信号处理—理论、应用及软件实现．重庆出版社，1997年2月．
[10]马兴义，杨立群等．Matlab 6应用开发指南．机械工业出版社，2002年1月．
[11]张德干．小波变换在数字图象处理中的应用研究．硕士学位论文，东北大学．2000年．
[12]陈自利．基于小波与神经网络的文字识别系统研究．博士学位论文，重庆大学．1999年．
[13]江亚东．KDD系统中基于小波神经网络的混沌模式提取与混沌时间序列预测的研究．博士学位论文，北京科技大学．2002年．
[14]钱峻．小波神经网络建摸研究与现场总线控制系统的集成．博士学位论文，上海交通大学．2000年．
[15]孟波．基于小波分析的数据挖掘方法研究．博士学位论文，南京大学．1994年．
[16]黄源．基于神经网络的数据挖掘技术研究研究．博士学位论文，南京大学．1994年．
[17]钱能主编．C++程序设计教程．清华大学出版社，1999年4月．
[18]Jon Bates，Tim Tompkins著，何健辉等译实用Visual C++6.0教程．清华大学出版社，2000年8月．
[19]向世明．Visual C++数字图象与图形处理．电子工业出版社，2002年3月．
[20]北京博彦科技发展有限公司．Visual C++编程高手．北京大学出版社，2000年11月．
[21]张青，尹俊勋．小波变换在手写体汉字识别中的应用．电路与系统学报，1996，(3)，63-67．
[22]张德于，郝先臣等．基于小波理论的数据挖掘方法研究．小型微型计算机系统，2001，22(8)，946-949．
[23]陈哲，冯天谨．小波分析与神经网络结合的研究进展．电子科学学刊，2000，22(3)，496-504．
[24]冯兵等．HMM方法识别脱机手写体汉字．模式识别与人工智能，2002，15(1)，84-88．
[25]金连文，黄建成等．变形变换及其在手写体汉字整形中的应用．中国图象图形学报，2002，7(2)，170-175．
[26]付新文，张妙兰等．基于小波生成特征符号随机场的纹理匹配与分类．中国图象图形学报，1999，4(3)，243-246．
[27]张睿，丁晓青等．脱机手写汉字识别的最优采样特征新方法．中国图象图形学报，2002，7(2)，176-180．
[28]文颖，龚裕等．基于基本笔画运笔特征的汉字笔迹鉴定的研究．上海交通大学学报(自然科学版)，2002，8(1)，39-43．
[29]杨懂峰等．计算机自动笔迹鉴定关键技术研究．计算机技术与自动化，2002，21(2)，27-34．
[30]刘成林等．基于多通道分解与匹配的笔迹鉴别研究．自动化学报，1997，23(1)，56-63．
[31]刘成林，戴汝为等．笔迹鉴别的字符预处理与匹配．中文信息学报，1996，10(3)．
[32]刘成林等．简化的Wigner分布及其在笔迹鉴别中的应用．计算机学报，1997，20(11)．
[33]林湘宁，刘沛等．小波分析基础理论及其在电力系统中的应用．电力系统自动化，1997，21(10)．
[34]许东，吴铮．基于MATLAB 6.x的系统分析与设计—神经网络．西安电子科技大学出版社，2002年5月．
[35]R. Plamondon and G. Lorret. Automation Signature Verification and Writer Identification-the State of Art. Pattern Recognition. 1989,22(2), 107-131.
[36]P. S. Deng, H. M. Liao, C. W. Ho and H. R. Tyan. Wavelet-based Off-line Signature Verification. http: //www.iis.sinica.edu.tw/LIB/threebone9717.html.
[37]Y. Y. Tang, F. Yang and J. Liu. Basic Processes of Chinese Character Based on Cubic BSpline Wavelet Transform. IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 23, no. 12, pp. 1443-1448, 2001.
[38]S. Sasi, L. Schwiebert and J. S. Bedi. Wavelet Packet Transform and Neuro Fuzzy Approach to Handwritten Character Recognition Signal and Image Proc. Conf.. 1997,12, pp. 129-133.
[39]R. S. R. Kunte, and R. D. S. Samuel. On-line Character Recognition for Handwritten Kannada Characters Using Wavelet Feature and Neural Classifier IETE Joural of Research. Vol. 46, no. 5, pp. 387-392, 2000.
[40]C. Barrire and R. Plamondon. Human Identification of Letter in MixedScript Handwriting: an Upper Bound on Recognition Rates IEEE Trans. On System, Man, and Cyber.-part B: Cyber. Vol. 28, no. 1, pp. 78-81, 1998.
[41]I. P. Morns and S. S. Dlay. Analog Design of a New Neural Network for Optical Charater Recognition. IEEE Trans. On Neural Networks. Vol. 10, no. 4, pp. 951-953, 1999.
[42]I. P. Morns and S. S. Dlay. The DSFPN, a New Neural Network for Optical Charater
Recongnition IEEE Trans. On Neural Networks. Vol. 10, no. 6, pp. 1465-1473, 1999.
[43]C. K. Tan, Y. L. Soh and C. Y. Woo. A Novel Method of Online Handwritten Chinese Word Verification. http://www. wbmt. tudelft.nl/pto/research/conferences/Proceedings/icsc/pdf.
[44]U. Bhattacharya, T. K. Das and B. B. Chaudhuri. A Cascaded Scheme for Recognition of Handprinted Numbers The 3rd Indian Conf. on Computer Vision, Graph. and Image Proc., Oral Session2: OCR. 2002.
[45]D. Shi, S. R. Gunn and R. I. Damper. A Radical Approach to Handwritten Chinese Character Recognition Using Active Handwriting Models Proc. IEEE Conf. On Computer Vision and Pattern Recognition. pp. 670-675, 2001.
[46]M. Morita, R. Sabourin et al. Segmentation and Recognition of Handwritten Dates The 8th Inter. Workshop on Frontiers in Handwriting Recognition. 8, 1999.
[47]R. Plamondon and N. Srihari. On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 22, no. 1, pp. 63-84, 2000.
[48]S. E. N. Correia et al. On the Performance of Wavelets for Handwritten Numerals Recognition The 16th Inter. Conf. on Pattern Recognition. Vol. Ⅲ, pp. 127-130, 2002.
[49]A. Mojsilovic, M. Popovic and J. Marinkovic. Texture Analysis and Classification with the Nonseparable Wavelet Transform. Circulation, 8, 1998.
[50]T. D. But and G. Chen. Invariant FourieWavelet Descriptor for Pattern Recognition Pattern Recognition. Vol. 32, no. 7, pp.1083-1088, 1999.
[51]G. Y. Chen. Application of Wavelet Transforms in Pattern Recogniion andDe-noise. MCS Thesis. Concordia University, Canada 1999,1.
[52]A. Vinviarelli. A Survey on Off-Line Cursive Script Recognition IDIAP-RR 00-43. 2000.
[53]S. E. U. Correia el al. Human-Perception Handwritten Character Recognition using Wavelets http://www.livia.etsmtl.ca/common/pub_2OO2.html.
[54]X. Gao, L. W. Jin, J. X. Yin and J. C.Huang. SVM-based Handwritten Chinese Character Recognition http://www.cse.cuhk.edu.hk/～apnna/proceedings/iconip2OO1/author/g.htm.
[55]S. Omachi, F. Sun and H. Aso. Precise Recognition of Blurred Chinese Characters by Considering Change in Distribution Proc. Of the 10th Scandinavian Conf. on Image Analysis. pp. 501-506, 1997.
[56]N. Rajpoot. Texture Classification Using Discriminant Wavelet Packet Subbands Proc. Of the 10th IEEE Midwest Symp. on Circuits and Systems, 2002.
[57]A. K. Pujari el al. An Adaption Character Recognition for Telugu Scripts using Multiresolution Analysis aud Associative Memory The 3rd Indian Conf. on Computer Vision, Graph. and
Image Proc., Oral Session2: OCR. 2002.
[58]P. J. Burr and E. H. Adelson. The Laplacian Pyamid as a Compact Image CodelEEE Trans, C-31. pp. 532-540, 1983.
[59]E. A. Fadhel and P. Bhattacharyya. Application of a Steerable WaveletTransform using Neural Network for Signature Verification Pattern Analysis and Applications. Vol. 2, Issue 2, pp. 184-195, 1999.
[60]C. C. Tappert et al. The State of the Art in On-line Handwriting Recognition IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 12, no. 8, pp. 787-805, 1990.
[61]E. Mandler, R. Oed. and W. Doster. Experiments in on-line script recognition, in Proc. 4th Scan-dinavian Conf. Image Anal. June, pp. 75-86, 1985.
[62]K. Huang and H. Yan. Off-line Signature Verification Based on Geometric Feature Extraction and Neural Network Classification Pattern Recognition. Vol. 30, no. 1, pp. 9-17, 1997.
[63]G. Y. Chen, T. D. Bui and A. Krzyzak Contour-Based Handwritten Recognition using Multiwavelet and Neural Networks Pattern Recognition. Vol. 36, no. 7, pp. 1597-1604, 2003.
[64]T. R. Reed and H. Wechsler. Segmentation of Tectured images and Gestart Organization using Spatial/Spatial-Frequency Representation IEEE Trans on PAMI. Vol. 12, no. 1, pp. 1-12, 1990.
[65]Y. Itoh et al. A Study on Estimation of High Resolution Component for Image Enhancement using Wavelet. Proc. Of the 7th ACM Inter. Conf. on Multimedia. Part: 2, 1999.
[66]S. Mallat and S. F. Zhong Characterization of Signals from Multiscale Edges IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 14, no. 7, pp. 710-732, 1992.
[67]S. Mallat. A Theory for Multiresolulion Signal Decomposition The Wavelet Representation IEEE Trans. On Pattern Analysis and Machine Intelligence. Vol. 11, no. 7, pp. 674-693, 1989.
[68]M. Feil and A. Uhl. 2-D Wavelet Packet Decomposition on Multicomputers. Proc, of the 8th Euromicro Workshop on Parallel and Distributed Proc, IEEE Computer Society. pp.351-356. 2000.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |